Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3258 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5590. Min Range: -7.5590
Max Act: 7.5590. Min Act: -0.1700
Data Index: 5814424 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5590. Min Range: -7.5590
Max Act: 7.4652. Min Act: -0.1700
Data Index: 856241 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.9965. Min Act: -0.1700
Data Index: 8367119 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.9027. Min Act: -0.1700
Data Index: 4266195 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.8715. Min Act: -0.1700
Data Index: 6890401 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.8090. Min Act: -0.1700
Data Index: 7860257 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.7777. Min Act: -0.1700
Data Index: 5000195 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.7465. Min Act: -0.1700
Data Index: 1883537 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.7465. Min Act: -0.1700
Data Index: 4812720 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.6840. Min Act: -0.1700
Data Index: 688608 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.6840. Min Act: -0.1700
Data Index: 4113037 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.6527. Min Act: -0.1700
Data Index: 8127189 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.6215. Min Act: -0.1700
Data Index: 3907640 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.3090. Min Act: -0.1700
Data Index: 2111196 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.2777. Min Act: -0.1700
Data Index: 4752937 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.2152. Min Act: -0.1700
Data Index: 8083259 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.1527. Min Act: -0.1700
Data Index: 1351184 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.1840. Min Act: -0.1700
Data Index: 6153127 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.1840. Min Act: -0.1700
Data Index: 8005516 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5590. Min Range: -7.5590
Max Act: 6.1527. Min Act: -0.1700
Data Index: 5023118 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19